mlsanityData to 14 Oct 2026

Enhancing Prediction Models with Reinforcement Learning

arXiv 2412.06791 ↗First posted 21 Nov 2024cs.IR cs.LGcited by 1

On the map: Deep reinforcement learning methods → RL training of language and agent models

Abstract (arXiv)

We present a large-scale news recommendation system implemented at Ringier Axel Springer Polska, focusing on enhancing prediction models with reinforcement learning techniques. The system, named Aureus, integrates a variety of algorithms, including multi-armed bandit methods and deep learning models based on large language models (LLMs). We detail the architecture and implementation of Aureus, emphasizing the significant improvements in online metrics achieved by combining ranking prediction models with reinforcement learning. The paper further explores the impact of different models mixing on key business performance indicators. Our approach effectively balances the need for personalized recommendations with the ability to adapt to rapidly changing news content, addressing common challenges such as the cold start problem and content freshness. The results of online evaluation demonstrate the effectiveness of the proposed system in a real-world production environment.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods. Builds on 2 of its 9 references that are in the map. First posted on arXiv 21 Nov 2024.

Builds on

2 of 9 references.

References · 2

  1. 2016Item2Vec: Neural Item Embedding for Collaborative Filteringcited by 72
  2. 2019Trend-responsive User Segmentation Enabling Traceable Publishing Insights. A Case Study of a Real-world Large-scale News Recommendation Systemcited by 2

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Solving cold start in news recommendations: a RippleNet-based system for large scale media outletcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Learning User Interests via Reasoning and Distillation for Cross-Domain News Recommendation
  2. 2025Deep Reinforcement Learning for Ranking Utility Tuning in the Ad Recommender System at Pinterest
  3. 2024Aligning Large Language Models for Controllable Recommendations
  4. 2019Deep Reinforcement Learning for Personalized Search Story Recommendation ↗
  5. 2024Optimizing Novelty of Top-k Recommendations using Large Language Models and Reinforcement Learning
  6. 2024Large Language Models are Learnable Planners for Long-Term Recommendation
  7. 2026Reasoning to Rank: An End-to-End Solution for Exploiting Large Language Models for Recommendation
  8. 2025DeepRec: Towards a Deep Dive Into the Item Space with Large Language Model Based Recommendation